Deloitte Dbrief - Visual Analytics: An Enhanced View into Corruption, Fraud, Waste, and Abuse?
Upcoming SlideShare
Loading in...5
×
 

Like this? Share it with your network

Share

Deloitte Dbrief - Visual Analytics: An Enhanced View into Corruption, Fraud, Waste, and Abuse?

on

  • 1,241 views

This is the slide deck from the 5/11/11 Deloitte Dbrief entitled, Visual Analytics: An Enhanced View into Corruption, Fraud, Waste, and Abuse? More companies are employing various data-driven analytic ...

This is the slide deck from the 5/11/11 Deloitte Dbrief entitled, Visual Analytics: An Enhanced View into Corruption, Fraud, Waste, and Abuse? More companies are employing various data-driven analytic techniques and methods, including visual analytics, for business intelligence purposes. How can visualization be employed to analyze potential corruption, fraud, waste, and abuse? The panelists discussed using visual analytics to identify business risks; visual analytics in the analysis of unstructured data, such as emails and instant messages; and enhancing continuous monitoring capabilities with visual analytics, and providing clarity to predictive and advanced analytics through visualization.

Statistics

Views

Total Views
1,241
Views on SlideShare
1,241
Embed Views
0

Actions

Likes
1
Downloads
39
Comments
0

0 Embeds 0

No embeds

Accessibility

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Deloitte Dbrief - Visual Analytics: An Enhanced View into Corruption, Fraud, Waste, and Abuse? Presentation Transcript

  • 1. Transactions & Business Events presents: Visual Analytics: An Enhanced View into Corruption, Fraud, Waste and AbuseAnthony DeSantis, Senior Manager, Deloitte Financial Advisory Services LLPMatt Gentile, Principal, Deloitte Financial Advisory Services LLPRichard Simon, Senior Manager, Deloitte Financial Advisory Services LLPDavid Williams, Chief Executive Officer, Deloitte Financial Advisory Services LLPMay 11, 2011
  • 2. AgendaIntroductionVisual analytics: It’s all about the dataEnhancing your view into corruption, fraud,waste and abuseApplications of visual analyticsQ&A Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 3. Release for answers to polling questionsUnderstand that any data or information provided by you as part of participating in this Dbriefswebcast (―webcast‖) may be used by Deloitte in connection with this webcast, other studies, oranalyses performed by Deloitte, publications, or in connection with services provided by Deloitteor otherwise.Understand that this webcast is the proprietary property of Deloitte.Understand that any such data or information may be disclosed by Deloitte to related entities orother third parties, including, without limitation, in publications, in connection with this webcast orsuch studies, analyses, or services, provided that such data or information does not contain anyinformation that identifies you or associates you with the data or information that you haveprovided or are providing.Understand disclosure of such data or information could be required by law, in which case Deloittewill endeavor to notify you. Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 4. Poll question #1Has your company ever used visual analytics techniques toidentify corruption, fraud, waste and abuse?• Yes• No• NA/Don’t know Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 5. Visual Analytics:It’s all about the data
  • 6. A new visual lexicon is evolving to communicaterich information about increasingly complex data Word clouds/tag clouds Social networks and community detection Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 7. Visual analytics is the science of analytical reasoning facilitated by interactive visual interfaces Cognition Exploration Visual queries Visual Analytical Interpretation Interactive feedback representation reasoning Decision-making Visual analytics Statistics Data Production and Monitoring Relationships Storytelling representation dissemination Data reduction CommunicatingFramework adapted from Linköping University, itn.lie.se/mit/research/information-and-geo-visualization/l=en Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 8. Exploring transactional data using visual analytictechniques Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 9. Poll question #2What is the most advanced visual analytic tool at yourcompany?• MS Excel• Business intelligence platforms• Specialized analytic software• Custom software• NA/Don’t know Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 10. Enhancing your viewinto corruption, fraud,waste and abuse
  • 11. Enhancing your view into corruption, fraud, waste and abuseSource: http://newsmap.jp/#/b,m,n,s,t,w/us/view/all/fraud/1 Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 12. Enhancing your view into corruption,fraud, waste and abuse • According to the ACFE, 40% of occupational fraud is Doing More identified via tip 1 With Less • Increased regulatory requirement • Limited resources (time, budget and people) • Every day, more and more electronic data is createdVolume of Data • Finding a needle in the haystack • Rules-based approaches may only take you so far • BI tools and other data mining software include visualTechnology & analytic capabilities Adoption • Analysts becoming accustomed to viewing data visually • Identify complex trends, patterns or anomalies 1. ACFE 2010 Report to the Nations on Occupational Fraud and Abuse Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 13. Enhancing your view into corruption,fraud, waste and abuse A n V a i l s y u t a i l c s Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 14. Applications of visual analytics
  • 15. Link analysis• Unexpected relationships• Anti-money laundering• Social Networks• e-Discovery Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 16. Beyond link analysis Treemaps• Accommodate hundreds or thousands of data points in one Doing More screen With Less• Patterns and exceptions can be spotted in seconds• Multiple dimensions can be displayed at the same time• Further enhanced with sliders and drilldown capabilities Doing More With Less BrazilGermany UK China Doing More US With Less -1 Percent Change Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 17. Applying modular algorithms and profiles to detectcandidate high-risk transactions Suspect transactions revealed by applying: • Classifications • Scoring algorithms • Complex profiles Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 18. Spatial analysis gets its start – proximity & correlation! In 1854, John Snow depicted a cholera outbreak in London using points to represent the locations of some individual cases, possibly the earliest use of the geographic method. His study of the distribution of cholera led to the source of the disease, a contaminated water pump (the Broad Street Pump, whose handle he had disconnected, thus terminating the outbreak) within the heart of the cholera outbreak. http://en.wikipedia.org/wiki/Geographic_information_system Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 19. No longer just static pictures –dynamic data! Racial breakdown of Chicago. Red is White (42%) Blue is Black (36.8%) Green is Asian (4.4%) Orange is Hispanic (26%) Gray is Other Each dot = 25 people Data from Census 2000 & 2010. Base map © OpenStreetMap, CC-BY-SA — Source: Eric Fischer http://www.radicalcartography.net/index.html?chicagodots Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 20. Geospatial Analytics  the collection,visualization and analysis of data that can be tied toa geographic location on, above or below theEarth’s surface.“Everything is related to everything else, but nearthings are more related than distant things.” Source: Tobler’s first law of geography of all data now has >80% a location component Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 21. How do we get there? Where is fraud, waste & abuse most likely to occur? Where is the greatest concentration of risk and opportunity? Geo-Analytics Business Intelligence & Geospatial Where to deploy my assets, tools and Intelligence resources to achieve the greatest Financial result or reach the greatest number of Intelligence customers? How can I shape policy to influence geographically localized behaviors?Financial dataTransactionsInstitutionsPeoplePlacesGoods/MaterialsContractsAddresses/lat/longTerritories Source: Sean Gorman, GeoIQ Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 22. Poll question #3Which is the most important reason to use geospatialanalytics in regards to mitigating corruption, fraud, waste andabuse at your company?• To determine where corruption, fraud, waste & abuse are most likely to occur• To determine where the greatest concentration of risk and opportunity lies• To determine where to deploy assets, tools and resources to achieve the greatest result or reach the greatest number of customers• To determine how to shape policy to influence geographic consumer behaviors• NA/Don’t know Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 23. Applied geospatial example:Medicare fraud
  • 24. A Geographic Information System (GIS)Transforms tabular data into location information Coordinates are assigned to spreadsheet data through a process called geocoding. This is a preliminary step in the analysis to identify fee-for-service fraud, such as Medicare fraud. The red points below symbolize the location of clinics in Miami, FL: (25.77981, -80.25141) HYPOTHETICAL SCENARIO © 2011 Deloitte Touche Tohmatsu Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 25. Features can be symbolized based on underlying data The same clinics are now represented by location and by the number of Medicare claims filed and a visual story begins to unfold. HYPOTHETICAL SCENARIO Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 26. Features can be symbolized based on underlying data A suspected bad actor is visually identified, but additional data and information is needed before moving forward. 24,000 claims 43,000 claims 10,000 claims 19,000 claims 7,000 claims 12,000 claims 18,000 claims HYPOTHETICAL SCENARIO Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 27. GIS integrates disparate data by overlaying multiple data sets The heat map below illustrates the prevalence of people over 65 years old and low income (highest concentration in red)*. The clinic in question is even more conspicuous because it does not reflect the socio-demographic profile of a beneficiary. Multiple data sets can be combined to create a service beneficiary (patient) profile using: •Socio-demographic information •Travel Distance/Time Data •Primary Care Service Area Data •Patient Address Information *Source: http://factfinder.census.gov/ HYPOTHETICAL SCENARIO Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 28. GIS integrates disparate data by overlaying multiple data sets We can also overlay market segmentation data on the clinic locations and run spatial queries to determine statistically significant relationships between a clinic location and the surrounding neighborhoods.Market demographicsare incongruous withbilling patterns.According to the marketsegmentation* data, area #12characterizes:•―Up and Coming Families‖•Average age of 39.1 years•Upper-middle class•Predominately White•Single-family units *Source: http://www.esri.com/data/esri_data/tapestry.html HYPOTHETICAL SCENARIO Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 29. Functionality for conducting robust statistical analysis is built-In Where are the outliers? By combining clinic location data ancillary socio-demographic data we can conduct a cluster/outlier analysis that can help us statistically find anomalous billing patterns when visual relationships are not visually discernable.A cluster analysis of patientaddresses (light blue points) reveals:•Patients are all retirement/nursinghome residents•Patients are low income seniorcitizens•They are outside of the averagedrive-time distance to a clinicWe can test our hypothesis using avariety of statistical tools built intoGIS, including:•Nearest Neighbor Analysis•Spatial Autocorrelation•Outlier Analysis•Linear Regression Analysis•Cluster Analysis HYPOTHETICAL SCENARIO Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 30. Poll question #4How much of an impact will the use of visual analytics todiscover fraud have on companies in the next 5 years?• Significant impact• Somewhat of an impact• Little to no impact• NA/Don’t know Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 31. Visual Analytics – Many possibilities• Exploring, not just visualizing the data• One size does not fit all• Structured and unstructured data Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 32. Questions and Answers
  • 33. Poll question #5Are you interested in receiving follow up articles and whitepapers surrounding today’s topic from Deloitte?• Yes• No• NA Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 34. Join us June 8th at 2 PM ET asour Transactions & BusinessEvents series presents:Delivering Value throughM&A: Improving CorporateDevelopment Effectiveness
  • 35. CPE certificates are now available for immediate download.Click the Request CPE link in the lower right hand corner of the screen. Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 36. Contact infoAnthony DeSantisSenior ManagerDeloitte Financial Advisory Services LLP+1 212 436 3307andesantis@deloitte.comMatt GentilePrincipalDeloitte Financial Advisory Services LLP+1 571 882 6880magentile@deloitte.comRichard SimonSenior ManagerDeloitte Financial Advisory Services LLP+1 212 436 3438risimon@deloitte.comDavid WilliamsChief Executive OfficerDeloitte Financial Advisory Services LLP+1 212 492 2879davidswilliams@deloitte.com Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 37. This presentation contains general information only and Deloitte is not, by means of thispresentation, rendering accounting, business, financial, investment, legal, tax, or otherprofessional advice or services. This presentation is not a substitute for such professional adviceor services, nor should it be used as a basis for any decision or action that may affect yourbusiness. Before making any decision or taking any action that may affect your business, youshould consult a qualified professional advisor. Deloitte shall not be responsible for any losssustained by any person who relies on this presentation. Copyright © 2011 Deloitte Development LLC. All rights reserved.
  • 38. About DeloitteDeloitte refers to one or more of Deloitte Touche Tohmatsu Limited, a UK private company limited byguarantee, and its network of member firms, each of which is a legally separate and independent entity.Please see www.deloitte.com/about for a detailed description of the legal structure of Deloitte ToucheTohmatsu Limited and its member firms. Please see www.deloitte.com/us/about for a detailed descriptionof the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attestclients under the rules and regulations of public accounting. Copyright © 2011 Deloitte Development LLC. All rights reserved.